© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3384
    Prev
    Next
    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consequences or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doesnt
    -0.65
     didnt
    -0.61
     dont
    -0.59
    DragonMagazine
    -0.59
     whats
    -0.53
     alot
    -0.52
     secondly
    -0.52
     thous
    -0.51
     tyr
    -0.51
    yss
    -0.50
    POSITIVE LOGITS
    *.
    1.17
    .*
    1.11
    .[
    1.10
    .''.
    1.09
    .</
    1.05
    .''
    1.01
    .).
    0.99
    .
    0.98
    .ãĢį
    0.98
    .�
    0.94
    Activations Density 2.329%

    No Known Activations